Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     or
    0.56
    궁
    0.56
     happening
    0.53
    或其他
    0.52
    NumConst
    0.52
    నించ
    0.52
     ஒவ்வொரு
    0.51
     perman
    0.50
     mỗi
    0.50
     clause
    0.49
    POSITIVE LOGITS
    钥匙
    0.58
    Си
    0.57
     보내
    0.57
     भोजन
    0.57
    篒
    0.55
     Си
    0.55
     ihn
    0.55
    imgs
    0.54
     STRU
    0.54
    YES
    0.54
    Act Density 0.233%

    No Known Activations